Classification tree analysis to evaluate the most useful magnetic resonance image type in the differentiation between early and progressed hepatocellular carcinoma.

AIM: Using classification tree analysis, we evaluated the most useful magnetic resonance (MR) image type in the differentiation between early and progressed hepatocellular carcinoma (eHCC and pHCC). METHODS: We included pathologically proven 214 HCCs (28 eHCCs and 186 pHCCs) in 144 patients. The signal intensity of HCCs was assessed on in-phase (T1in) and opposed-phase T1-weighted images (T1op), ultrafast T2-weighted images (ufT2WI), fat-saturated T2-weighted images (fsT2WI), diffusion-weighted images (DWI), contrast enhanced T1-weighted images in the arterial phase (AP), portal venous phase (PVP), and the hepatobiliary phase. Fat content and washout were also evaluated. Fisher's exact test was performed to evaluate usefulness for the differentiation. Then, we chose MR images using binary logistic regression analysis and performed classification and regression tree analysis with them. Diagnostic performances of the classification tree were evaluated using a stratified 10-fold cross-validation method. RESULTS: T1in, ufT2WI, fsT2WI, DWI, AP, PVP, fat content, and washout were all useful for the differentiation (p < 0.05), and AP and T1in were finally chosen for creating classification trees (p < 0.05). AP appeared in the first node in the tree. The area under the curve, sensitivity and specificity for eHCC, and balanced accuracy of the classification tree were 0.83 (95% CI 0.74-0.91), 0.64 (18/28, 95% CI 0.46-0.82), 0.94 (174/186, 95% CI 0.90-0.97), and 0.79 (95% CI 0.70-0.87), respectively. CONCLUSIONS: AP is the most useful MR image type and T1in the second in the differentiation between eHCC and pHCC.

Is using a consolidation tumor ratio 0.5 as criterion feasible in daily practice? Evaluation of interobserver measurement variability of consolidation tumor ratio of lung cancer less than 3 cm in size.

BACKGROUND: Consolidation tumor ratio (CTR) calculated as the ratio of the tumor consolidation diameter to the tumor maximum diameter on thin-section computed tomography (CT) of lung cancer has been reported as an important prognostic factor. It has also been used for treatment decision-making. This study aimed to investigate the interobserver variability of CTR measurements on preoperative CT and propose a clinically useful CTR-based classification criterion. METHODS: We enrolled 119 patients who underwent surgery for suspected or diagnosed small-sized lung cancer (≤3.0 cm in diameter). Nine doctors reviewed preoperative CT scans to measure CTR. Interobserver variability of CTR measurements was evaluated using the coefficient of variation (CV) and Fleiss' κ. The prognostic effect of the CTR-based classification was assessed using the Kaplan-Meier method. RESULTS: Interobserver variability of CTR measurement was the highest for tumors with the lowest CTR (CTR = 0); it decreased as CTR increased and reached a plateaued level of low variability (CV <0.5) at CTR of 0.5. We proposed a three-group classification based on the findings of CTR interobserver variability (CTR < 0.5, 0.5 ≤ CTR < 1, and CTR = 1). Interobserver agreement of the judgment of the CTR-based classification was excellent (Fleiss' κ = 0.81). The classification significantly stratified patient prognosis (p < 0.001, 5-year overall survival rates with CTR < 0.5, 0.5 ≤ CTR < 1, and CTR = 1 were 100, 88, and 73.8%, respectively). CONCLUSIONS: CTR 0.5 is a clinically relevant and helpful cutoff for treatment decision-making in patients with early-stage lung cancer based on high interobserver agreement and good prognostic stratification.

Useful preoperative examination findings to classify the grade of ovarian primary mucinous tumor.

PURPOSE: To evaluate various imaging features on magnetic resonance imaging (MRI) and tumor markers and their utility to assess various grades of ovarian primary mucinous tumors (OPMTs): benign, borderline, or malignant. METHODS: Ninety-five pathologically diagnosed OPMTs [53 benign, 24 borderline malignant (BM), and 18 malignant] were selected in this retrospective study. MRI features of the ovarian mass, namely the maximum diameter, honeycomb loculi, solid components (SC), stained-glass pattern, and signal intensity of the cyst on T1- (T1WI) and T2-weighted imaging (T2WI) with/without fat suppression, and preoperative STMs, namely carcinoembryonic antigen (CEA), carbohydrate antigen (CA) 19-9, and CA125, were compared between the three tumor grades using univariate analysis. We also analyzed the findings to estimate the pathological diagnosis using classification tree (CT) analysis. RESULTS: Maximum diameter, honeycomb loculi, SC, stained-glass pattern, signal intensity of the cyst [hyperintensity on both T1WI and T2WI (T1-hyper/T2-hyper), and hyperintense on T1WI and hypointense on T2WI (T1-hyper/T2-hypo)], and CEA and CA 19-9 concentrations were significantly different between the three tumor grades (p < 0.05). The concordance rate with the pathological diagnosis was the highest with diagnosis by the CT comprising T1-hyper/T2-hypo, CEA, and CA 19-9 and by the CT comprising T1-hyper/T2-hypo, CEA, and SC. CONCLUSION: Four types of findings were important for OPMT grading. Lesions negative for both T1-hyper/T2-hypo and CEA suggest benign; lesions positive for T1-hyper/T2-hypo and negative for CA 19-9 or SC suggest BM; and lesions negative for T1-hyper/T2-hypo and positive for CEA, or positive for both T1-hyper/T2-hypo and CA 19-9 or SC suggest malignancy.

Spontaneous Regression of Radiologically Diagnosed Epidermoid Cyst Originating from the Cerebellopontine Angle.

BACKGROUND: Generally, asymptomatic epidermoid cysts (ECs) or ECs with minor symptoms controlled by medication are not treated further. Although epidermoid carcinomas are only sporadically reported, the possibility of malignant transformation of ECs is of concern. CASE DESCRIPTION: A 77-year-old man under observation for a left cerebellopontine angle tumor presented with no symptoms, including headache, dizziness, or other cranial nerve abnormalities typical of cerebellopontine angle tumors. The tumor manifested as an extra-axial mass in the left cerebellopontine angle and measured 24 × 16 mm (length × width) on magnetic resonance imaging (MRI). As he was asymptomatic, his primary physician did not pursue invasive treatment but ordered follow-up MRI every 2 years. The tumor decreased in size 2 years after the initial MRI, and no tumor fragmentation was observed on the patient's spinal MRI. Ultimately, the tumor shrank to 19 × 11 mm over 22 years. CONCLUSIONS: The reduction of an EC is extremely rare. We report a case of spontaneous regression of an EC and consider similar previous cases.

Dynamic contrast-enhanced computed tomography diagnosis of primary liver cancers using transfer learning of pretrained convolutional neural networks: Is registration of multiphasic images necessary?

PURPOSE: To evaluate the effect of image registration on the diagnostic performance of transfer learning (TL) using pretrained convolutional neural networks (CNNs) and three-phasic dynamic contrast-enhanced computed tomography (DCE-CT) for primary liver cancers. METHODS: We retrospectively evaluated 215 consecutive patients with histologically proven primary liver cancers, including six early, 58 well-differentiated, 109 moderately differentiated, 29 poorly differentiated hepatocellular carcinomas (HCCs), and 13 non-HCC malignant lesions containing cholangiocellular components. We performed TL using various pretrained CNNs and preoperative three-phasic DCE-CT images. Three-phasic DCE-CT images were manually registered to correct respiratory motion. The registered DCE-CT images were then assigned to the three color channels of an input image for TL: pre-contrast, early phase, and delayed phase images for the blue, red, and green channels, respectively. To evaluate the effects of image registration, the registered input image was intentionally misaligned in the three color channels by pixel shifts, rotations, and skews with various degrees. The diagnostic performances (DP) of the pretrained CNNs after TL in the test set were compared by three general radiologists (GRs) and two experienced abdominal radiologists (ARs). The effects of misalignment in the input image and the type of pretrained CNN on the DP were statistically evaluated. RESULTS: The mean DPs for histological subtype classification and differentiation in primary malignant liver tumors on DCE-CT for GR and AR were 39.1%, and 47.9%, respectively. The highest mean DPs for CNNs after TL with pixel shifts, rotations, and skew misalignments were 44.1%, 44.2%, and 43.7%, respectively. Two-way analysis of variance revealed that the DP is significantly affected by the type of pretrained CNN (P = 0.0001), but not by misalignments in input images other than skew deformations. CONCLUSION: TL using pretrained CNNs is robust against misregistration of multiphasic images and comparable to experienced ARs in classifying primary liver cancers using three-phasic DCE-CT.