Qualitative and Quantitative Contrast-Enhanced Ultrasound Combined with Conventional Ultrasound for Predicting the Malignancy of Soft Tissue Tumors

Contrast-enhanced ultrasound reveals perfusion differences between benign lipoma and semi-malignant atypical lipomatous tumors: A prospective clinical study

PURPOSE

Soft tissue tumors (STT) are difficult to diagnose accurately, and distinguishing between benign and malignant tumors is challenging. Lipoma is the most common STT, while atypical lipomatous tumors (ALT) can dedifferentiate into malignant lipomatous tumors like grade 1 liposarcoma and require more radical therapy. This study aims to investigate the potential of contrast-enhanced ultrasound (CEUS) to differentiate between lipoma and ALT based on tumor perfusion.

MATERIALS AND METHODS

We prospectively examined 52 patients who were scheduled for biopsy for suspected lipoma or ALT. The CEUS examination was performed using SonoVue as a contrast agent to quantify tumor perfusion using VueBox V7.1 software. Peak enhancement (PE), rise time (RT), wash-in perfusion index (WiPI), and wash-out rate (WoR) were used to assess contrast enhancement inside the STT.

RESULTS

Among 50 tumors examined, 30 were lipomas, and 20 were ALTs. We found significant differences in perfusion between lipomas and ALTs (PE: 49.22 ± 45.75 a.u. vs. 165.67 ± 174.80; RT: 23.86 ± 20.47s vs. 10.72 ± 5.34 s; WiPI: 33.06 ± 29.94 dB vs. 107.21 ± 112.43 dB; WoR: 2.44 ± 3.70 dB/s vs. 12.75 ± 15.80 dB/s; p<.001). ROC analysis of PE resulted in a diagnostic accuracy of 74% for the detection of an ALT, and 77% for the detection of a lipoma.

CONCLUSION

CEUS may enhance the differential diagnosis of benign lipomas and ALTs, with ALTs showing higher levels of perfusion. If larger prospective studies confirm these findings, CEUS could enhance diagnostic accuracy, guide surgical planning, and potentially reduce unnecessary treatments for patients presenting with ambiguous lipomatous tumors like lipoma or ALT.

A practical risk stratification system based on ultrasonography and clinical characteristics for predicting the malignancy of soft tissue masses

OBJECTIVE

To establish a practical risk stratification system (RSS) based on ultrasonography (US) and clinical characteristics for predicting soft tissue masses (STMs) malignancy.

METHODS

This retrospective multicenter study included patients with STMs who underwent US and pathological examinations between April 2018 and April 2023. Chi-square tests and multivariable logistic regression analyses were performed to assess the association of US and clinical characteristics with the malignancy of STMs in the training set. The RSS was constructed based on the scores of risk factors and validated externally.

RESULTS

The training and validation sets included 1027 STMs (mean age, 50.90 ± 16.64, 442 benign and 585 malignant) and 120 STMs (mean age, 51.93 ± 17.90, 69 benign and 51 malignant), respectively. The RSS was constructed based on three clinical characteristics (age, duration, and history of malignancy) and six US characteristics (size, shape, margin, echogenicity, bone invasion, and vascularity). STMs were assigned to six categories in the RSS, including no abnormal findings, benign, probably benign (fitted probabilities [FP] for malignancy: 0.001-0.008), low suspicion (FP: 0.008-0.365), moderate suspicion (FP: 0.189-0.911), and high suspicion (FP: 0.798-0.999) for malignancy. The RSS displayed good diagnostic performance in the training and validation sets with area under the receiver operating characteristic curve (AUC) values of 0.883 and 0.849, respectively.

CONCLUSION

The practical RSS based on US and clinical characteristics could be useful for predicting STM malignancy, thereby providing the benefit of timely treatment strategy management to STM patients.

CRITICAL RELEVANCE STATEMENT

With the help of the RSS, better communication between radiologists and clinicians can be realized, thus facilitating tumor management.

KEY POINTS

There is no recognized grading system for STM management. A stratification system based on US and clinical features was built. The system realized great communication between radiologists and clinicians in tumor management.

From Benign Lipoma to G3 Liposarcoma: Contrast-Enhanced Ultrasound Reveals Tumor Microperfusion and Indicates Malignancy

OBJECTIVE

Lipomatous soft tissue tumors (STT), ranging from benign lipomas to malignant liposarcomas, require accurate differentiation for timely treatment. Complementary to MRI, Contrast-enhanced ultrasound (CEUS) is emerging as a promising tool, providing insight into tumor microperfusion in real-time. This study aims to explore the potential of preoperative CEUS in differentiating benign lipomatous tumors from malignant liposarcoma subtypes.

METHODS

Eighty-seven patients with lipomatous STT scheduled for surgery were enrolled. Clinical and MRI assessments were conducted to obtain general tumor characteristics. CEUS was used for a standardized tumor perfusion evaluation. Perfusion analysis included peak enhancement, rise time, wash-in perfusion index, and wash-out rate, reflecting the perfusion kinetics. Histopathological results were obtained for every STT and compared to perfusion characteristics.

RESULTS

In total, 48 lipoma, 23 ALT and 11 liposarcoma were identified. Significant differences in tumor microperfusion were demonstrated, with higher perfusion levels indicating higher malignancy (Peak enhancement [a.u.] of Lipoma: 145 ± 238; ALT: 268 ± 368; Liposarcoma: 3256 ± 4333; p (ALT vs. Liposarcoma) < 0.001). A perfusion-based identification of a benign lipoma or ALT versus sarcoma resulted in a positive predictive value of 93%. Patient-related factors (age, gender, BMI, ASA score, smoking status) had no significant impact on the CEUS-based perfusion parameters.

CONCLUSION

Our study suggests CEUS as a capable non-invasive tool for improving preoperative assessment of lipomatous STT. It can assist in the distinction between benign and malignant STT, accelerating treatment decisions and enhancing patient outcomes. Significant correlations between CEUS-derived parameters and malignancy highlight its risk assessment potential.

Preoperative Classification of Peripheral Nerve Sheath Tumors on MRI Using Radiomics

Malignant peripheral nerve sheath tumors (MPNSTs) are aggressive soft-tissue tumors prevalent in neurofibromatosis type 1 (NF1) patients, posing a significant risk of metastasis and recurrence. Current magnetic resonance imaging (MRI) imaging lacks decisiveness in distinguishing benign peripheral nerve sheath tumors (BPNSTs) and MPNSTs, necessitating invasive biopsies. This study aims to develop a radiomics model using quantitative imaging features and machine learning to distinguish MPNSTs from BPNSTs. Clinical data and MRIs from MPNST and BPNST patients (2000-2019) were collected at a tertiary sarcoma referral center. Lesions were manually and semi-automatically segmented on MRI scans, and radiomics features were extracted using the Workflow for Optimal Radiomics Classification (WORC) algorithm, employing automated machine learning. The evaluation was conducted using a 100× random-split cross-validation. A total of 35 MPNSTs and 74 BPNSTs were included. The T1-weighted (T1w) MRI radiomics model outperformed others with an area under the curve (AUC) of 0.71. The incorporation of additional MRI scans did not enhance performance. Combining T1w MRI with clinical features achieved an AUC of 0.74. Experienced radiologists achieved AUCs of 0.75 and 0.66, respectively. Radiomics based on T1w MRI scans and clinical features show some ability to distinguish MPNSTs from BPNSTs, potentially aiding in the management of these tumors.

Deep learning driven diagnosis of malignant soft tissue tumors based on dual-modal ultrasound images and clinical indexes

Background

Soft tissue tumors (STTs) are benign or malignant superficial neoplasms arising from soft tissues throughout the body with versatile pathological types. Although Ultrasonography (US) is one of the most common imaging tools to diagnose malignant STTs, it still has several drawbacks in STT diagnosis that need improving.

Objectives

The study aims to establish this deep learning (DL) driven Artificial intelligence (AI) system for predicting malignant STTs based on US images and clinical indexes of the patients.

Methods

We retrospectively enrolled 271 malignant and 462 benign masses to build the AI system using 5-fold validation. A prospective dataset of 44 malignant masses and 101 benign masses was used to validate the accuracy of system. A multi-data fusion convolutional neural network, named ultrasound clinical soft tissue tumor net (UC-STTNet), was developed to combine gray scale and color Doppler US images and clinic features for malignant STTs diagnosis. Six radiologists (R1-R6) with three experience levels were invited for reader study.

Results

The AI system achieved an area under receiver operating curve (AUC) value of 0.89 in the retrospective dataset. The diagnostic performance of the AI system was higher than that of one of the senior radiologists (AUC of AI vs R2: 0.89 vs. 0.84, p=0.022) and all of the intermediate and junior radiologists (AUC of AI vs R3, R4, R5, R6: 0.89 vs 0.75, 0.81, 0.80, 0.63; p <0.01). The AI system also achieved an AUC of 0.85 in the prospective dataset. With the assistance of the system, the diagnostic performances and inter-observer agreement of the radiologists was improved (AUC of R3, R5, R6: 0.75 to 0.83, 0.80 to 0.85, 0.63 to 0.69; p<0.01).

Conclusion

The AI system could be a useful tool in diagnosing malignant STTs, and could also help radiologists improve diagnostic performance.

Ultrasound performance in pediatric deep soft-tissue tumor characterization

This study investigated the performance of ultrasonography in diagnosing deep soft-tissue tumors and tumor-like lesions in children with histological results. Demographic information and ultrasound characteristics of benign and malignant masses were statistically analyzed. Three radiologists (Radiologists 1, 2, and 3) independently reviewed the ultrasonography studies while being blinded to the medical history and other imaging findings. The 82 lesions included in the study were histopathologically classified as malignant (n = 25) or benign (n = 57). No statistically significant differences were observed between the benign and malignant subgroups regarding age (p = 0.059), sex (p = 1.0), disease course (p = 0.812), presence or absence of symptoms (p = 0.534), maximum diameter (p = 0.359), margin (p = 1.0), calcification (p = 0.057), or blood Adler type (p = 0.563). However, statistically significant differences were observed between the benign and malignant subgroups in terms of isolated or Multiple occurrences (p < 0.001), history of malignancy (p < 0.001), shape (p < 0.001), and echogenicity (p < 0.001). Parameters such as tumor shape (p = 0.042, OR = 6.222), single or multiple occurrences (p = 0.008, OR = 17.000), and history of malignancy (p = 0.038, OR = 13.962) were identified as independent predictors of benign and malignant tumors. The diagnostic sensitivities evaluated by the three radiologists were 68.0%, 72.0%, 96.0%, respectively, while the specificities were 77.2%, 82.5%, 77.2%, respectively. Ultrasound demonstrates good performance in the diagnosis of benign deep lesions such as hemangiomas/venous malformation and adipocytic tumors. Multiple irregular morphologies and a history of malignancy were identified as independent risk factors for malignant masses. The experience of radiologists in recognizing specific tumors is important. Careful attention should be paid to masses with ambiguous ultrasound features, as well as small lesions.

Practical approach to ultrasound of soft tissue tumors and the added value of MRI: how I do it

This review outlines a practical approach to the everyday assessment of both non-neoplastic and neoplastic soft tissue tumors, focusing on ultrasound examination, though emphasizing the added benefit of magnetic resonance imaging in certain instances. Ultrasound approach and assessment, practical scenarios, reporting, biopsy, and follow-up are covered, as well as the criteria used to distinguish benign from malignant tumors. The potential benefits and current limitations of elastography and contrast-enhanced ultrasound in assessment are also addressed. Examples of commonly encountered soft tissue tumors are shown. Ultrasound can characterize most soft tissue masses based on their ultrasound appearance alone. Following ultrasound examination, three potential scenarios usually exist in clinical practice: (a) confident regarding diagnosis, (b) indeterminate mass with no evidence of malignancy, and (c) indeterminate mass with possibility of malignancy. A diagnostic pathway for each of these scenarios is provided. Magnetic resonance imaging is generally not helpful in further characterizing masses which are indeterminate on ultrasound assessment, though it is helpful in addressing other issues such as exact tumor location and neurovascular bundle involvement that may not be fully resolved on ultrasound examination. In these situations, magnetic resonance imaging examination can be tailored to address those specific questions that have not been adequately addressed on ultrasound examination. In this sense, both examinations are highly complementary. Tips for undertaking magnetic resonance imaging examinations are provided.

Analysis on diagnostic failure of US-guided core needle biopsy for soft tissue tumors

Purpose

To evaluate the diagnostic yield of ultrasonography (US)-guided core needle biopsy (CNB) in the diagnosis of soft tissue tumors (STTs) and to analyze the failure factors.

Methods

139 patients with STTs that underwent both US-guided CNB and surgical resection were collected retrospectively. Compared with the histopathological results of surgical resection, the biopsy failure was defined as the following conditions: indefinitive diagnosis, including insufficient samples and unknown subtypes with correct biological potential classification; wrong diagnosis, including wrong biological potential classification and wrong subtypes with correct biological potential classification. Univariate and multivariate analyses from the perspectives of histopathological, demographic and US features together with biopsy procedures were performed to determine risk factors for diagnostic failure.

Results

The diagnostic yield of US-guided CNB for STTs in our study was 78.4%, but when only considering the correct biological potential classification of STTs, the diagnostic yield was 80.6%. The multivariate analysis showed that adipocytic tumors (odds ratio (OR) = 10.195, 95% confidence interval (CI): 1.062 - 97.861, p = 0.044), vascular tumors (OR = 41.710, 95% CI: 3.126 - 556.581, p = 0.005) and indeterminate US diagnosis (OR = 8.641, 95% CI: 1.852 - 40.303, p = 0.006) were correlated with the diagnostic failure. The grade III vascular density (OR = 0.019, 95% CI: 0.001 - 0.273, p = 0.007) enabled a higher diagnostic accuracy.

Conclusion

US-guided CNB can be an effective modality for the diagnosis of STTs. The diagnostic yield can be increased when the tumor vascular density was grade III in Color Doppler US, but can be decreased in adipocytic tumors, vascular tumors and masses with indeterminate US diagnosis.

Added value of contrast-enhanced ultrasound to conventional ultrasound for characterization of indeterminate soft-tissue tumors

OBJECTIVE

To assess the added value of contrast-enhanced ultrasound (CEUS) to conventional ultrasound in differentiating benign soft-tissue tumors from malignant ones.

METHODS

197 soft-tissue tumors underwent ultrasound examination with confirmed histopathology were retrospectively evaluated. The radiologists classified all the tumors as benign, malignant, or indeterminate according to ultrasound features. The indeterminate tumors underwent CEUS were reviewed afterwards for malignancy identification by using individual and combined CEUS features.

RESULTS

Ultrasound analysis classified 62 soft-tissue tumors as benign, 111 tumors as indeterminate and 24 tumors as malignant. There 104 indeterminate tumors were subject to CEUS. Three CEUS features including enlargement of enhancement area, infiltrative enhancement boundary, and intratumoral arrival time difference were significantly associated with the tumor nature in both univariable and multivariable analysis for the indeterminate tumors (all p < 0.05). When at least one out of the three discriminant CEUS features were present, the best sensitivity of 100% for malignancy identification was obtained with the specificity of 66.7% and the AUC of 0.833. When at least two of the three discriminant CEUS features were present, the best area under the receiver operating characteristic curve (AUC) of 0.924 for malignancy identification was obtained. The combination of at least two discriminant CEUS features showed much better diagnostic performance than the optimal combination of ultrasound features in terms of AUC (0.924 vs 0.608, p < 0.0001), sensitivity (94.0% vs 42.0%, p < 0.0001), and specificity (90.7% vs 79.6%, p = 0.210) for the indeterminate tumors.

CONCLUSION

The combination CEUS features of enlargement of enhancement area, infiltrative enhancement boundary and intratumoral arrival time difference are valuable to improve the discriminating performance for indeterminate soft-tissue tumors on conventional ultrasound.

ADVANCES IN KNOWLEDGE

The combination of peritumoral and arrival-time CEUS features can improve the discriminating performance for indeterminate soft-tissue tumors on conventional ultrasound.