Incremental Learning with SVM for Multimodal Classification of Prostatic Adenocarcinoma

Abstract

Robust detection of prostatic cancer is a challenge due to the multitude of variants and their representation in MR images. We propose a pattern recognition system with an incremental learning ensemble algorithm using support vector machines (SVM) tackling this problem employing multimodal MR images and a texture-based information strategy. The proposed system integrates anatomic, texture, and functional features. The data set was preprocessed using B-Spline interpolation, bias field correction and intensity standardization. First- and second-order angular independent statistical approaches and rotation invariant local phase quantization (RI-LPQ) were utilized to quantify texture information. An incremental learning ensemble SVM was implemented to suit working conditions in medical applications and to improve effectiveness and robustness of the system. The probability estimation of cancer structures was calculated using SVM and the corresponding optimization was carried out with a heuristic method together with a 3-fold cross-validation methodology. We achieved an average sensitivity of 0.844±0.068 and a specificity of 0.780±0.038, which yielded superior or similar performance to current state of the art using a total database of only 41 slices from twelve patients with histological confirmed information, including cancerous, unhealthy non-cancerous and healthy prostate tissue. Our results show the feasibility of an ensemble SVM being able to learn additional information from new data while preserving previously acquired knowledge and preventing unlearning. The use of texture descriptors provides more salient discriminative patterns than the functional information used. Furthermore, the system improves selection of information, efficiency and robustness of the classification. The generated probability map enables radiologists to have a lower variability in diagnosis, decrease false negative rates and reduce the time to recognize and delineate structures in the prostate.

Computer-aided Detection of Prostate Cancer with MRI

“…The combination of anatomic (T2W) images and functional techniques has been shown to increase the accuracy of MR imaging for diagnosis of PCa. Table 1 compares the performance of the major published prostate CADx systems [13, 14, 16–18, 22, 26, 27, 36, 37, 39, 51, 52, 54–57, 62, 122, 129, 140–151]. Chan et al.…”

“…For cases in which radiologists are less confident, they can get higher performance by using the computer output. A recent study showed a pattern recognition system enables radiologists to have a lower variability in diagnosis, decreases false negative rates, and reduces the time to recognize and delineate structures in the prostate [16]. The benefit of CADx also includes guiding biopsy using cancer location information from MRI [14].…”

Automated prostate cancer detection using T2‐weighted and high‐b‐value diffusion‐weighted magnetic resonance imaging

“…Several CAD systems adopting a multiparametric approach have been developed. T2W MRI was combined with DCE MRI, 8,9 diffusion-weighted imaging (DWI), 10 or MR spectroscopy. 11,12 Some incorporated T2W MRI, DCE MRI, and DWI together.…”

“…[13][14][15][16][17][18][19][20] Intensity 8,10,[13][14][15][16]19 and texture [9][10][11]16,18 features were commonly used to characterize suspicious lesions. Texture features included first-order statistics, 9,16 co-occurrence matrix, 10,16 gradient operators, 16,18 local binary pattern, 18 local phase quantization, 9 and wavelet transform. 11 In addition, graph embedding, 12,21 random walk, 17 locally linear embedding, 15 and principal component analysis 11 were used to reduce data dimension and/or to improve data representation.…”

“…22,23 Cancer detection in the transition zone or central gland is more challenging in part because cancers can be masked by adjacent benign prostatic hyperplasia (BPH). 9,23 T2W MRI, DCE MRI, and a map of apparent diffusion coefficient (ADC) from DWI have been the mainstay of multiparametric MRI in the previous studies. In addition to these, high-b-value DWI has recently gained much attention and shown a capability for tissue and tumor characterization and detection in the brain, 24 breast, 25 colon, 26 gallbladder, 27 liver, 28 pancreas, 29 and prostate.…”