Learnable image histograms-based deep radiomics for renal cell carcinoma grading and staging

Fuhrman cancer grading and tumor-node-metastasis (TNM) cancer staging systems are typically used by clinicians in the treatment planning of renal cell carcinoma (RCC), a common cancer in men and women worldwide. Pathologists typically use percutaneous renal biopsy for RCC grading, while staging is performed by volumetric medical image analysis before renal surgery. Recent studies suggest that clinicians can effectively perform these classification tasks non-invasively by analyzing image texture features of RCC from computed tomography (CT) data. However, image feature identification for RCC grading and staging often relies on laborious manual processes, which is error prone and time-intensive. To address this challenge, this paper proposes a learnable image histogram in the deep neural network framework that can learn task-specific image histograms with variable bin centers and widths. The proposed approach enables learning statistical context features from raw medical data, which cannot be performed by a conventional convolutional neural network (CNN). The linear basis function of our learnable image histogram is piece-wise differentiable, enabling back-propagating errors to update the variable bin centers and widths during training. This novel approach can segregate the CT textures of an RCC in different intensity spectra, which enables efficient Fuhrman low (I/II) and high (III/IV) grading as well as RCC low (I/II) and high (III/IV) staging. The proposed method is validated on a clinical CT dataset of 159 patients from The Cancer Imaging Archive (TCIA) database, and it demonstrates 80% and 83% accuracy in RCC grading and staging, respectively.

[1]  Elaine M Caoili,et al.  Renal mass core biopsy: accuracy and impact on clinical management. , 2007, AJR. American journal of roentgenology.

[2]  M. Stöckle,et al.  Survival outcomes in patients with large (≥7cm) clear cell renal cell carcinomas treated with nephron-sparing surgery versus radical nephrectomy: Results of a multicenter cohort with long-term follow-up , 2018, PloS one.

[3]  Junhua Zheng,et al.  Clinical use of a machine learning histopathological image signature in diagnosis and survival prediction of clear cell renal cell carcinoma , 2020, International journal of cancer.

[4]  C. Porta,et al.  Renal cell carcinoma: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. , 2012, Annals of oncology : official journal of the European Society for Medical Oncology.

[5]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[6]  Jonathan Scalera,et al.  Texture analysis as a radiomic marker for differentiating renal tumors , 2017, Abdominal Radiology.

[7]  E. S. Durmaz,et al.  Unenhanced CT Texture Analysis of Clear Cell Renal Cell Carcinomas: A Machine Learning-Based Study for Predicting Histopathologic Nuclear Grade. , 2019, AJR. American journal of roentgenology.

[8]  Min Ju Kim,et al.  Correlation of CT imaging features and tumor size with Fuhrman grade of clear cell renal cell carcinoma , 2017, Acta radiologica.

[9]  H. Huhdanpaa,et al.  CT prediction of the Fuhrman grade of clear cell renal cell carcinoma (RCC): towards the development of computer-assisted diagnostic method , 2015, Abdominal Imaging.

[10]  N. Takahashi,et al.  CT and MR imaging for solid renal mass characterization. , 2018, European journal of radiology.

[11]  John L. Gore,et al.  Long-term survival following partial vs radical nephrectomy among older patients with early-stage kidney cancer. , 2012, JAMA.

[12]  R. Thornhill,et al.  Importance of phase enhancement for machine learning classification of solid renal masses using texture analysis features at multi-phasic CT , 2020, Abdominal Radiology.

[13]  Changhee Han,et al.  Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-Based CT Image Augmentation for Object Detection , 2019, 2019 International Conference on 3D Vision (3DV).

[14]  A. Molina,et al.  Validation of risk factors for recurrence of renal cell carcinoma: Results from a large single-institution series , 2019, PloS one.

[15]  Zhan Feng,et al.  CT texture analysis: a potential tool for predicting the Fuhrman grade of clear-cell renal carcinoma , 2019, Cancer Imaging.

[16]  Lei Wang,et al.  3D cGAN based cross-modality MR image synthesis for brain tumor segmentation , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[17]  Fabien Scalzo,et al.  Deep learning and radiomics: the utility of Google TensorFlow™ Inception in classifying clear cell renal cell carcinoma and oncocytoma on multiphasic CT , 2019, Abdominal Radiology.

[18]  Paul F. Whelan,et al.  Using filter banks in Convolutional Neural Networks for texture classification , 2016, Pattern Recognit. Lett..

[19]  Ghassan Hamarneh,et al.  Generalizable Feature Learning in the Presence of Data Bias and Domain Class Imbalance with Application to Skin Lesion Classification , 2019, MICCAI.

[20]  Choung-Soo Kim,et al.  Percutaneous Kidney Biopsy for a Small Renal Mass: A Critical Appraisal of Results. , 2016, The Journal of urology.

[21]  Fan Lin,et al.  CT-based machine learning model to predict the Fuhrman nuclear grade of clear cell renal cell carcinoma , 2019, Abdominal Radiology.

[22]  H. Pyo,et al.  Body fat measurement in computed tomography image. , 1999, Biomedical sciences instrumentation.

[23]  M. Janghorbani,et al.  The comparative survey of Hounsfield units of stone composition in urolithiasis patients , 2014, Journal of research in medical sciences : the official journal of Isfahan University of Medical Sciences.

[24]  Xiaogang Wang,et al.  Learnable Histogram: Statistical Context Features for Deep Neural Networks , 2016, ECCV.

[25]  C. Sundaram,et al.  CT texture analysis in the differentiation of major renal cell carcinoma subtypes and correlation with Fuhrman grade , 2019, European Radiology.

[26]  D. Holanda,et al.  Tumor grade of clear cell renal cell carcinoma assessed by contrast-enhanced computed tomography , 2014, SpringerPlus.

[27]  Stephen M. Moore,et al.  The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository , 2013, Journal of Digital Imaging.

[28]  M. Kattan,et al.  A preoperative prognostic nomogram for solid enhancing renal tumors 7 cm or less amenable to partial nephrectomy. , 2007, The Journal of urology.

[29]  Jiule Ding,et al.  CT-based radiomic model predicts high grade of clear cell renal cell carcinoma. , 2018, European journal of radiology.

[30]  J. Patard,et al.  Can renal mass biopsy assessment of tumor grade be safely substituted for by a predictive model? , 2009, The Journal of urology.

[31]  Qi Cheng,et al.  Enhanced Computed Tomography–Based Radiomics Signature Combined With Clinical Features in Evaluating Nuclear Grading of Renal Clear Cell Carcinoma , 2020, Journal of computer assisted tomography.

[32]  S. Fuhrman,et al.  Prognostic significance of morphologic parameters in renal cell carcinoma , 1982, The American journal of surgical pathology.

[33]  B. Iványi,et al.  Prognostic Factors for Renal Cell Carcinoma Subtypes Diagnosed According to the 2016 WHO Renal Tumor Classification: a Study Involving 928 Patients , 2017, Pathology & Oncology Research.

[34]  Mohammad Reza Deevband,et al.  Noninvasive Fuhrman grading of clear cell renal cell carcinoma using computed tomography radiomic features and machine learning , 2019, La radiologia medica.

[35]  P. Tan,et al.  Differential radiologic characteristics of renal tumours on multiphasic computed tomography. , 2017, Singapore medical journal.

[36]  S. Meystre,et al.  Automated Extraction and Classification of Cancer Stage Mentions fromUnstructured Text Fields in a Central Cancer Registry , 2018, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[37]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[38]  V. Ramani,et al.  Accuracy of preoperative CT T staging of renal cell carcinoma: which features predict advanced stage? , 2015, Clinical radiology.

[39]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[40]  A. Oberai,et al.  Shape and texture-based radiomics signature on CT effectively discriminates benign from malignant renal masses , 2020, European Radiology.

[41]  Ghassan Hamarneh,et al.  Renal Cell Carcinoma Staging with Learnable Image Histogram-Based Deep Neural Network , 2019, MLMI@MICCAI.

[42]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  H. Yin,et al.  Clear cell renal cell carcinoma: CT-based radiomics features for the prediction of Fuhrman grade. , 2018, European journal of radiology.

[44]  J. Cheville,et al.  The International Society of Urological Pathology (ISUP) Grading System for Renal Cell Carcinoma and Other Prognostic Parameters , 2013, The American journal of surgical pathology.

[45]  J. Earls,et al.  Texture analysis and machine learning algorithms accurately predict histologic grade in small (< 4 cm) clear cell renal cell carcinomas: a pilot study , 2019, Abdominal Radiology.

[46]  Xiaopeng He,et al.  Grading of Clear Cell Renal Cell Carcinomas by Using Machine Learning Based on Artificial Neural Networks and Radiomic Signatures Extracted From Multidetector Computed Tomography Images. , 2020, Academic radiology.

[47]  C. Meyer,et al.  Critical analysis of a simplified Fuhrman grading scheme for prediction of cancer specific mortality in patients with clear cell renal cell carcinoma--Impact on prognosis. , 2016, European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology.

[48]  O. Kilickesmez,et al.  Clear Cell Renal Cell Carcinoma: Machine Learning-Based Quantitative Computed Tomography Texture Analysis for Prediction of Fuhrman Nuclear Grade , 2018, European Radiology.

[49]  Ghassan Hamarneh,et al.  Noninvasive Determination of Gene Mutations in Clear Cell Renal Cell Carcinoma Using Multiple Instance Decisions Aggregated CNN , 2018, MICCAI.

[50]  Ghassan Hamarneh,et al.  ImHistNet: Learnable Image Histogram Based DNN with Application to Noninvasive Determination of Carcinoma Grades in CT Scans , 2019, MICCAI.

[51]  Xiaoli Meng,et al.  Clear cell renal cell carcinoma: Machine learning-based computed tomography radiomics analysis for the prediction of WHO/ISUP grade. , 2019, European journal of radiology.

[52]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[53]  Michael J Schwartz,et al.  Partial Nephrectomy is Associated with Higher Risk of Relapse Compared with Radical Nephrectomy for Clinical Stage T1 Renal Cell Carcinoma Pathologically Up Staged to T3a , 2017, The Journal of urology.

[54]  Mitko Veta,et al.  Automated clear cell renal carcinoma grade classification with prognostic significance , 2019, PloS one.

[55]  Lin Liu,et al.  Prediction of ISUP grading of clear cell renal cell carcinoma using support vector machine model based on CT images , 2019, Medicine.

[56]  E. Bass,et al.  Diagnostic Accuracy and Risks of Biopsy in the Diagnosis of a Renal Mass Suspicious for Localized Renal Cell Carcinoma: Systematic Review of the Literature. , 2016, The Journal of urology.