Patient-Level Prediction of Multi-Classification Task at Prostate MRI Based on End-to-End Framework Learning From Diagnostic Logic of Radiologists

Abstract

The grade groups (GGs) of Gleason scores (Gs) is the most critical indicator in the clinical diagnosis and treatment system of prostate cancer. End-to-end method for stratifying the patient-level pathological appearance of prostate cancer (PCa) in magnetic resonance (MRI) are of high demand for clinical decision. Existing methods typically employ a statistical method for integrating slice-level results to a patient-level result, which ignores the asymmetric use of ground truth (GT) and overall optimization. Therefore, more domain knowledge (e.g. diagnostic logic of radiologists) needs to be incorporated into the design of the framework. The patient-level GT is necessary to be logically assigned to each slice of a MRI to achieve joint optimization between slice-level analysis and patient-level decision-making. In this paper, we propose a framework (PCa-GGNet-v2) that learns from radiologists to capture signs in a separate two-dimensional (2-D) space of MRI and further associate them for the overall decision, where all steps are optimized jointly in an end-to-end trainable way. In the training phase, patient-level prediction is transferred from weak supervision to supervision with GT. An association route records the attentional slice for reweighting loss of MRI slices and interpretability. We evaluate our method in an in-house multi-center dataset (N=570) and PROSTATEx (N=204), which yields fiveclassification accuracy over 80% and AUC of 0.804 at patient-level respectively. Our method reveals the state-of-

Predicting clinically significant prostate cancer with a deep learning approach: a multicentre retrospective study

“…Thus, DL has been widely used in the AI-aided diagnosis of various cancers, such as lung cancer, breast cancer, and other diseases [15,16]. AI has been used to aid in the diagnosis and treatment of PCa [17][18][19]. Recently, some studies have developed DL models based on bpMRI images without DCE images to diagnose csPCa [13,20].…”

Dual attention guided multiscale neural network trained with curriculum learning for noninvasive prediction of Gleason Grade Group from MRI

“…Since integrating slice‐level prediction grades into a patient‐level result directly through a voting‐based strategy (e.g., majority‐voting, mean, or maximum) is not reasonable in this multiclass classification task, 25 the lesion area weighted method was used to postprocess slice‐level prediction probabilities instead (Figure 6): $$$$\begin{eqnarray} {P_{{\rm{patient}}}} = \sum\nolimits_{i = 0}^n {\omega {P_{{\rm{slice}}}}} \;, \omega \; = \frac{{{S_{{\rm{slice}}}}}} {{{S_{{\rm{all}}}}}}\;,\nonumber \\[5pt] \quad {\rm{\;}} {P_{{\rm{slice}}}} = \left( {{p_1},{p_2},{p_3},{p_4},{p_5}} \right){\rm{\;}} \in \left[ {0,{\rm{\;}}1} \right],\end{eqnarray}$$$$where ω represents the area weight of each slice, n the number of slices for a patient. Each channel probability in P slice is independent ranging from 0 to 1.…”

“…Since integrating slice-level prediction grades into a patient-level result directly through a voting-based strategy (e.g., majority-voting, mean, or maximum) is not reasonable in this multiclass classification task, 25 the lesion area weighted method was used to postprocess slice-level prediction probabilities instead (Figure 6):…”

A Deep Learning Approach for Predicting Clinically Significant Prostate Cancer: A Retrospective, Multicentre Study

“…It has great potentials for reducing the inconsistencies between observers and improving the diagnostic accuracy [9][10][11][12], and has been widely used in the AI-aided diagnosis of a various of cancers, such as lung cancer, breast cancer and other diseases [13,14]. In particular, AI has been used to aid in diagnosing and treating PCa [15][16][17]. Recently, some studies constructed deep learning models based on bpMRI images without DCE images to diagnose csPCa [11,18].…”